Unsupervised Discovery of Emphysema Subtypes in a Large Clinical Cohort

  • Polina BinderEmail author
  • Nematollah K. Batmanghelich
  • Raul San Jose Estepar
  • Polina Golland
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10019)


Emphysema is one of the hallmarks of Chronic Obstructive Pulmonary Disorder (COPD), a devastating lung disease often caused by smoking. Emphysema appears on Computed Tomography (CT) scans as a variety of textures that correlate with disease subtypes. It has been shown that the disease subtypes and textures are linked to physiological indicators and prognosis, although neither is well characterized clinically. Most previous computational approaches to modeling emphysema imaging data have focused on supervised classification of lung textures in patches of CT scans. In this work, we describe a generative model that jointly captures heterogeneity of disease subtypes and of the patient population. We also describe a corresponding inference algorithm that simultaneously discovers disease subtypes and population structure in an unsupervised manner. This approach enables us to create image-based descriptors of emphysema beyond those that can be identified through manual labeling of currently defined phenotypes. By applying the resulting algorithm to a large data set, we identify groups of patients and disease subtypes that correlate with distinct physiological indicators.


Feature Vector Compute Tomography Scan Force Vital Capacity Disease Subtype Physiological Indicator 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Regan, E.A., Hokanson, J.E., et al.: Genetic epidemiology of COPD (COPDGene) study design. COPD 7(1), 32–43 (2010)CrossRefGoogle Scholar
  2. 2.
    Aziz, Z., Wells, A., et al.: HRCT diagnosis of diffuse parenchymal lung disease: inter-observer variation. Thorax 59(6), 506–511 (2004)CrossRefGoogle Scholar
  3. 3.
    Raghunath, S., Rajagopalan, S., et al.: Quantitative stratification of diffuse parenchymal lung diseases. PloS ONE 9, e93229 (2014)CrossRefGoogle Scholar
  4. 4.
    Blaiotta, C., Cardoso, M.J., et al.: Variational inference for image segmentation. Comput. Vis. Image Underst. (2016)Google Scholar
  5. 5.
    Mendoza, C., Washko, G., et al.: Emphysema quantification in a multi-scanner HRCT cohort using local intensity distributions. In: 2012 9th IEEE International Symposium on Biomedical Imaging (ISBI), pp. 474–477 (2012)Google Scholar
  6. 6.
    Prasad, M., Sowmya, A., et al.: Multi-level classification of emphysema in HRCT lung images. Pattern Anal. Appl. 11(1), 9–20 (2006)MathSciNetGoogle Scholar
  7. 7.
    Batmanghelich, N.K., Saeedi, A., Cho, M., Estepar, R.S.J., Golland, P.: Generative method to discover genetically driven image biomarkers. In: Ourselin, S., Alexander, D.C., Westin, C.-F., Cardoso, M.J. (eds.) IPMI 2015. LNCS, vol. 9123, pp. 30–42. Springer, Heidelberg (2015). doi: 10.1007/978-3-319-19992-4_3 CrossRefGoogle Scholar
  8. 8.
    Hame, Y., Angelini, E.D., et al.: Sparse sampling and unsupervised learning of lung texture patterns in pulmonary emphysema: MESA COPD study. In: 2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI), pp. 109–113. IEEE (2015)Google Scholar
  9. 9.
    Efron, B., Tibshirani, R.J.: An Introduction to the Bootstrap. Chapman & Hall, New York (1993)CrossRefzbMATHGoogle Scholar
  10. 10.
    Vinh, N.X., Epps, J., et al.: Information theoretic measures for clusterings comparison: variants, properties, normalization and correction for chance. J. Mach. Learn. Res. 11, 2537–2854 (2010)MathSciNetzbMATHGoogle Scholar

Copyright information

© Springer International Publishing AG 2016

Authors and Affiliations

  • Polina Binder
    • 1
    Email author
  • Nematollah K. Batmanghelich
    • 2
  • Raul San Jose Estepar
    • 2
  • Polina Golland
    • 1
  1. 1.Computer Science and Artificial Intelligence Lab, EECSMITCambridgeUSA
  2. 2.Brigham and Womens HospitalHarvard Medical SchoolBostonUSA

Personalised recommendations